Vehicle control method and system for rain and snow weather, and vehicle terminal

Abstract

The application relates to the technical field of vehicle control, and discloses a vehicle control method and system for rainy and snowy weather and a vehicle terminal. The application obtains weather-related parameters corresponding to a target vehicle, and if the weather-related parameters satisfy preset first-level determination conditions, snow ground identification is performed on a road surface on which the target vehicle travels, a wet and slippery road surface area in the road surface is obtained, and when the target vehicle travels in the wet and slippery road surface area, the target vehicle is controlled to start an automatic braking function. If the weather-related parameters satisfy rainy and snowy weather conditions, it is determined that snow may appear on the road surface, snow ground identification is performed on the road surface on which the target vehicle travels, a wet and slippery road surface area is obtained, and when the vehicle is in the wet and slippery road surface area, the target vehicle is controlled to brake according to a collision risk level, automatic emergency braking of the vehicle in the wet and slippery road surface area is realized, obstacle avoidance support is provided for the vehicle in the wet and slippery road surface area, and the safety of vehicle travel is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, and particularly relates to a vehicle control method and system for rainy and snowy weather and a vehicle terminal. BACKGROUND

[0002] In winter, especially when it is rainy and snowy, the common existence of snow and ice on the road greatly affects the braking performance of vehicles, leading to a significant increase in braking distance and a substantial decrease in vehicle control stability, thus increasing the risk of traffic accidents. Therefore, safety driving systems such as anti-lock brake system (ABS) and electronic stability controller (ESC) play a crucial role in rainy and snowy weather. They can monitor the dynamic state of the vehicle in real time through built-in sensors and advanced control algorithms, and quickly adjust the brake pressure and engine output when detecting wheel slip or vehicle instability, thus effectively avoiding vehicle slip and instability and maintaining the stability and control of the vehicle.

[0003] However, safety driving systems such as anti-lock brake system and electronic stability controller mainly rely on vehicle sensor data and control strategies to identify the current road conditions, and they cannot perceive the environmental information in advance, thus failing to provide support for vehicle obstacle avoidance, resulting in low vehicle safety in rainy and snowy weather. SUMMARY

[0004] To have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not a general review, nor is it intended to determine key / important components or delineate the scope of protection of these embodiments, but as a prelude to the detailed description below.

[0005] In view of the above-mentioned disadvantages of the prior art, the present application provides a vehicle control method and system for rainy and snowy weather and a vehicle terminal to provide vehicle obstacle avoidance support in rainy and snowy weather, thus improving vehicle safety.

[0006] The application provides a vehicle control method for rainy and snowy weather, comprising: acquiring weather-related parameters corresponding to the target vehicle, wherein the weather-related parameters comprise driving environment parameters and / or tire adhesion parameters; if the weather-related parameters meet a preset first-level determination condition, performing target recognition on the road surface on which the target vehicle travels to obtain a road surface recognition result, wherein the first-level determination condition is determined by vehicle testing in different test environments, and the test environments comprise rainy and snowy weather environments; if the road surface recognition result meets a preset second-level determination condition, predicting the collision risk of the target vehicle to obtain a collision risk level, and controlling the target vehicle to brake according to the collision risk level, wherein the second-level determination condition comprises that the target vehicle is in a wet and slippery road surface area.

[0007] In an embodiment of the application, if the weather-related parameters meet the preset first-level determination condition, the method further comprises: acquiring car-road cooperation data and network map data; generating road condition information of the target vehicle according to the car-road cooperation data and the network map data; and playing the road condition information to a user in the target vehicle.

[0008] In an embodiment of the application, whether the road surface recognition result meets the second-level determination condition is determined by: acquiring sensor parameters collected by a plurality of vehicle sensors arranged on the target vehicle; performing path planning according to the sensor parameters to obtain a vehicle driving path of the target vehicle; if the road surface recognition result comprises a wet and slippery road surface area, mapping the target vehicle and the wet and slippery road surface area to the vehicle driving path, and simulating target vehicle driving according to the vehicle driving path to determine whether the target vehicle drives in the wet and slippery road surface area according to the simulation result.

[0009] In an embodiment of the present application, the path planning is performed according to the sensor parameters, and a vehicle driving path of the target vehicle is obtained, including: classifying the sensor parameters according to different parameter types, and performing data fusion on the sensor parameters of the same parameter type to obtain fusion data, wherein the fusion data includes global data and real-time data, the global data includes map data and / or road condition data, and the real-time data includes image sensor data and / or radar sensor data; if the global data includes map data, setting a starting position and a target position in the map data, and performing path planning between the starting position and the target position according to the global data to obtain a vehicle driving path; performing environment perception on an environment in which the target vehicle is located according to the real-time data to obtain environment perception data, and adjusting the vehicle driving path according to the environment perception data to avoid collision of the target vehicle with the target obstacle, wherein the environment perception data includes an obstacle position and / or an obstacle motion trajectory corresponding to the target obstacle.

[0010] In an embodiment of the present application, the collision risk of the target vehicle is predicted to obtain a collision risk level, and the target vehicle is controlled to brake according to the collision risk level, including: obtaining a deceleration matching table, wherein the deceleration matching table stores a plurality of original parameters, a reference deceleration corresponding to each of the original parameters, and an advanced deceleration corresponding to each of the original parameters, and the reference deceleration corresponding to the original parameter is smaller than the advanced deceleration corresponding to the original parameter; in response to identifying a target obstacle corresponding to the target vehicle, obtaining a collision risk parameter, wherein the collision risk parameter includes at least one of a relative distance between the target vehicle and the target obstacle, a relative speed between the target vehicle and the target obstacle, a collision time between the target vehicle and the target obstacle, a tire friction coefficient of the target vehicle, and a tire slip rate of the target vehicle; determining a collision risk level according to the collision risk parameter; if the collision risk level is greater than a preset level threshold and the target vehicle is in a normal area, determining a target deceleration from the reference deceleration according to a matching result between the collision risk parameter and the original parameter, and controlling the target vehicle to brake at the target deceleration, wherein the normal area is different from the wet and slippery road area; if the collision risk level is greater than the preset level threshold and the target vehicle is in the wet and slippery road area, determining a target deceleration from the advanced deceleration according to a matching result between the collision risk parameter and the original parameter, and controlling the target vehicle to brake at the target deceleration.

[0011] In an embodiment of the present application, the target deceleration is determined from the advanced decelerations according to the matching result between the collision risk parameters and the original parameters, including at least one of the following: determining intermediate decelerations corresponding to the collision risk parameters respectively from the advanced decelerations according to the matching result between the collision risk parameters and the original parameters, and taking the maximum intermediate deceleration as the target deceleration according to the comparison result between the intermediate decelerations; obtaining parameter priorities corresponding to the collision risk parameters respectively, and taking the collision risk parameter in the first order as the current parameter according to the parameter priorities; obtaining the reference parameter interval corresponding to the current parameter in response to the current parameter; if the current parameter is within the reference parameter interval, determining the target parameter from the advanced decelerations according to the matching result between the current parameter and the original parameter; if the current parameter is outside the reference parameter interval, taking the collision risk parameter in the next order as the new current parameter according to the parameter priorities.

[0012] In an embodiment of the present application, if the road surface recognition result meets the preset secondary determination condition, the method further includes at least one of the following: generating road surface prompt information, wherein the road surface prompt information is used to prompt a user in the target vehicle that the target vehicle is in a wet and slippery road surface area; if the relative distance between the target vehicle and the target obstacle is less than a preset warning distance, generating risk prompt information, wherein the risk prompt information is used to prompt the user in the target vehicle that the target vehicle has a collision risk.

[0013] In an embodiment of the present application, the method further includes: iteratively training an environment algorithm model according to preset training sample data to optimize model parameters of the environment algorithm model, wherein the environment algorithm model includes a target recognition model and / or an environment perception model, the target recognition model is used for target recognition of a road surface on which the target vehicle travels, and the environment perception model is used for identifying a target obstacle corresponding to the target vehicle; parameter optimizing the environment algorithm model according to user feedback data corresponding to the environment algorithm model; iteratively updating the environment algorithm model according to a model accuracy rate corresponding to the environment algorithm model until the model accuracy rate reaches a preset accuracy rate; obtaining environment sample data corresponding to different environment requirements respectively, and iteratively training the environment algorithm model according to the environment sample data to optimize the model parameters of the environment algorithm model, wherein the environment requirements include one or more of light conditions, environment conditions, and temperature conditions.

[0014] The application provides a vehicle control system for rainy and snowy weather, comprising: an acquisition module, configured to acquire weather-related parameters corresponding to the target vehicle, wherein the weather-related parameters comprise driving environment parameters and / or tire adhesion parameters; a first-level determination module, configured to, if the weather-related parameters meet preset first-level determination conditions, perform target identification on a road surface on which the target vehicle drives, to obtain a road surface identification result, wherein the first-level determination conditions are determined by vehicle testing in different test environments, and the test environments comprise rainy and snowy weather environments; and a second-level determination module, configured to, if the road surface identification result meets preset second-level determination conditions, predict a collision risk of the target vehicle, to obtain a collision risk level, so as to control the target vehicle to brake according to the collision risk level, wherein the second-level determination conditions comprise that the target vehicle is in a wet and slippery road surface area.

[0015] The application provides a vehicle terminal, comprising: a processor and a memory; the memory is configured to store a computer program, and the processor is configured to execute the computer program stored in the memory, so that the vehicle terminal executes the method described above.

[0016] The application has the following beneficial effects:

[0017] By acquiring weather-related parameters corresponding to the target vehicle, and if the weather-related parameters meet preset first-level determination conditions, performing snow identification on a road surface on which the target vehicle drives, to obtain a wet and slippery road surface area in the road surface, so that when the target vehicle drives in the wet and slippery road surface area, the target vehicle is controlled to start an automatic braking function. In this way, if the weather-related parameters meet rainy and snowy weather conditions, it is determined that snow may appear on the road surface, so that snow identification is performed on a road surface on which the target vehicle drives, to obtain a wet and slippery road surface area, and when the vehicle is in the wet and slippery road surface area, the target vehicle is controlled to brake according to a collision risk level, automatic emergency braking of the vehicle in the wet and slippery road surface area is realized, obstacle avoidance support is provided for the vehicle in the wet and slippery road surface area, and the safety of vehicle driving is improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a flowchart of a vehicle control method for rainy and snowy weather in an embodiment of the application;

[0019] Figure 2 is a structural diagram of a target vehicle provided with a vehicle sensor in an embodiment of the application;

[0020] Figure 3 is a flowchart of another vehicle control method for rainy and snowy weather in an embodiment of the application;

[0021] Figure 4is a flowchart of another vehicle control method for rainy and snowy weather in the embodiments of the present application;

[0022] Figure 5 is a structural diagram of a system architecture for implementing a vehicle control method for rainy and snowy weather in the embodiments of the present application;

[0023] Figure 6 is a structural diagram of a vehicle control system for rainy and snowy weather in the embodiments of the present application;

[0024] Figure 7 is a structural diagram of a vehicle terminal in the embodiments of the present application. DETAILED DESCRIPTION

[0025] The advantages and effects of the present application can be easily understood by those skilled in the art from the above description. The present application can also be implemented or applied in other different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and sub-samples in the embodiments can be combined with each other without conflict.

[0026] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner, and only the components related to the present application are shown in the diagrams, not the number, shape and size of the components when actually implemented. The actual implementation of each component may be a random change, and the component layout pattern may be more complex.

[0027] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application, however, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details, and in other embodiments, the known structures and devices are shown in the form of block diagrams rather than in the form of details, to avoid making the embodiments of the present application difficult to understand.

[0028] The terms "first", "second", and the like in the specification and claims of the embodiments of the present disclosure and the above-described diagrams are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0029] Unless otherwise specified, the term "a plurality of" means two or more.

[0030] In the embodiments of the present disclosure, the character " / " represents an "or" relationship between the preceding and following objects. For example, A / B means A or B.

[0031] The term "and / or" is a description of the association relationship between objects, which means that there can be three relationships. For example, A and / or B means that there are three relationships of A or B, or A and B.

[0032] In combination Figure 1 As shown, the embodiments of the present disclosure provide a vehicle control method for rainy and snowy weather, comprising:

[0033] In step S101, a weather-related parameter corresponding to a target vehicle is obtained.

[0034] The weather-related parameter includes a driving environment parameter and / or a tire adhesion parameter.

[0035] In step S102, if the weather-related parameter meets a preset first-level determination condition, the road surface on which the target vehicle travels is identified to obtain a road surface identification result.

[0036] The first-level determination condition is determined by vehicle testing in different test environments, and the test environment includes a rainy and snowy weather environment.

[0037] In step S103, if the road surface identification result meets a preset second-level determination condition, the collision risk of the target vehicle is predicted to obtain a collision risk level, so as to control the target vehicle to brake according to the collision risk level.

[0038] The second-level determination condition includes that the target vehicle is in a wet and slippery road surface area.

[0039] The vehicle control method for rainy and snowy weather provided by the embodiments of the present disclosure obtains the weather-related parameter corresponding to the target vehicle, and if the weather-related parameter meets the preset first-level determination condition, the road surface on which the target vehicle travels is identified to obtain the wet and slippery road surface area in the road surface, so that when the target vehicle travels in the wet and slippery road surface area, the automatic braking function of the target vehicle is controlled. In this way, if the weather-related parameter meets the rainy and snowy weather condition, it is judged that there may be snow on the road surface, so that the road surface on which the target vehicle travels is identified to obtain the wet and slippery road surface area, and when the vehicle is in the wet and slippery road surface area, the target vehicle is controlled to brake according to the collision risk level, realizing the automatic emergency braking of the vehicle in the wet and slippery road surface area, providing obstacle avoidance support for the vehicle in the wet and slippery road surface area, and improving the safety of vehicle driving.

[0040] Optionally, a plurality of vehicle sensors provided in the target vehicle are used to collect data to obtain sensor parameters collected by each vehicle sensor.

[0041] In some embodiments, the target vehicle is provided with a plurality of vehicle sensors, including: an image sensor for image acquisition around the target vehicle; a radar sensor for acquiring point cloud data around the target vehicle; a temperature sensor for acquiring the ambient temperature of the environment in which the target vehicle is located; a map system for acquiring map data from a server end; a tire rotation speed sensor for acquiring the vehicle speed of the target vehicle; a vehicle-to-everything (V2X) system for acquiring environmental information around the vehicle.

[0042] In combination Figure 2 As shown, the vehicle front, vehicle top, vehicle bottom and vehicle tail of the target vehicle are each provided with a temperature sensor and an image sensor, and the four wheels of the target vehicle are each provided with an image sensor and a tire rotation speed sensor.

[0043] In some embodiments, the lens of the image sensor has an automatic heating function for defrosting and defogging.

[0044] In some embodiments, the driving environment parameters include at least one of the ambient temperature, the ambient light intensity, and the weather parameter.

[0045] In some embodiments, the first-level determination condition corresponding to the ambient temperature includes that the ambient temperature is less than or equal to a preset temperature threshold, wherein the preset temperature threshold includes 0-5°C (degrees Celsius).

[0046] In some embodiments, the first-level determination condition corresponding to the weather parameter includes that the weather parameter is rainy, snowy or hailing weather.

[0047] In some embodiments, the tire adhesion parameter includes a tire friction coefficient and / or a tire slip ratio.

[0048] In some embodiments, the tire friction coefficient is calculated by the current vehicle speed and the braking distance at the current vehicle speed.

[0049] In some embodiments, the tire friction coefficient is calculated by formula (1):

[0050]

[0051] In formula (1), μ is the tire friction coefficient, v is the current vehicle speed, S1 is the braking distance at the current vehicle speed, and g is the acceleration of gravity, generally g is 9.81 m / s 2 .

[0052] In some embodiments, the tire slip ratio is calculated by the body movement speed and the wheel movement speed.

[0053] In some embodiments, the tire slip ratio is calculated by formula (2):

[0054]

[0055] Optionally, if the weather-related parameter meets the preset first-level determination condition, the method further includes: obtaining cooperative vehicle infrastructure system data and network map data; generating road condition information of the target vehicle according to the cooperative vehicle infrastructure system data and the network map data; and playing the road condition information to a user in the target vehicle.

[0056] In some embodiments, through the map data and / or the cooperative vehicle infrastructure system data, broadcast communication information, red light information, surrounding vehicle information, and road information on the road can be obtained on the driving path of the vehicle, so as to predict the road surface and traffic conditions in advance and take preventive measures.

[0057] In some embodiments, the cooperative vehicle infrastructure system data covers various communication modes such as vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), vehicle-to-pedestrian (V2P), vehicle-to-cloud (V2C), vehicle-to-network (V2N), and vehicle-to-traffic facility (V2T), and the core is to use wireless communication and Internet technologies to enable vehicles and the surrounding environment to exchange information and cooperate, thereby improving the safety, efficiency, and comfort of road traffic.

[0058] In some embodiments, through the cooperative vehicle infrastructure system data, the vehicle can obtain information such as the position, speed, and driving intention of surrounding vehicles in real time, thereby avoiding collisions and congestion; through the cooperative vehicle infrastructure system data, the vehicle can receive traffic information such as traffic lights and road construction, and make driving adjustments in advance; through the cooperative vehicle infrastructure system data, the vehicle can remind pedestrians to pay attention to traffic safety and reduce the risk of traffic accidents.

[0059] Optionally, whether the road surface recognition result meets the second-level determination condition is determined by: performing path planning according to the sensor parameters to obtain a vehicle driving path of the target vehicle; if the road surface recognition result includes a wet and slippery road surface area, mapping the target vehicle and the wet and slippery road surface area to the vehicle driving path, and simulating driving of the target vehicle according to the vehicle driving path to determine whether the target vehicle drives in the wet and slippery road surface area according to a simulation result.

[0060] In some embodiments, the wet and slippery road surface area includes at least one of a snow accumulation area, a water accumulation area, and a wet area.

[0061] In some embodiments, the target recognition is performed on the road surface on which the target vehicle travels to obtain a road surface recognition result, including: performing image acquisition on the road surface on which the target vehicle travels through an image sensor arranged on the target vehicle to obtain a road surface image, and performing target recognition on the road surface image through a preset image recognition model to obtain a wet and slippery road surface area in the road surface.

[0062] In some embodiments, the target recognition is performed on the road surface on which the target vehicle travels to obtain a road surface recognition result, including: performing image acquisition on the road surface on which the target vehicle travels through an image sensor arranged on the target vehicle to obtain a road surface image, and obtaining a preset reference image corresponding to the road surface, so as to determine a wet and slippery road surface area in the road surface according to a comparison result between the road surface image and the preset reference image.

[0063] In some embodiments, the snow field recognition is performed on the road surface on which the target vehicle travels to obtain a wet and slippery road surface area, including: receiving a snow accumulation area and a water accumulation area in a preset map range through a map system arranged on the target vehicle, and determining the wet and slippery road surface area according to an intersection between a vehicle path and a snow field road section, wherein the preset map range is determined by taking a vehicle position of the target vehicle as a range center.

[0064] Optionally, the vehicle driving path of the target vehicle is planned according to the sensor parameters, including: classifying the sensor parameters according to different parameter types, and fusing the sensor parameters of the same parameter type to obtain fusion data, wherein the fusion data includes global data and real-time data, the global data includes map data and / or road condition data, and the real-time data includes image sensor data and / or radar sensor data; if the global data includes the map data, a starting position and a target position are set in the map data, so as to plan the vehicle driving path between the starting position and the target position according to the global data; the environment in which the target vehicle is located is perceived according to the real-time data to obtain environment perception data, so as to adjust the vehicle driving path according to the environment perception data to avoid collision of the target vehicle with a target obstacle, wherein the environment perception data includes an obstacle position and / or an obstacle motion trajectory corresponding to the target obstacle.

[0065] In some embodiments, data from different vehicle sensors is fused according to different parameter types to provide an environmental view of the environment in which the vehicle is located, wherein the vehicle sensors include an image sensor, a radar sensor, a measurement unit, a global positioning system, a T-BOX, etc.

[0066] In some embodiments, environment perception is performed according to the fusion data, i.e., recognizing and understanding target objects in the environment view, including road boundaries, traffic signs, other vehicles, pedestrians, obstacles, etc. This process mainly uses image processing and machine learning techniques, and plays an important role in environment perception by recognizing patterns in images and classifying objects.

[0067] In some embodiments, path planning includes two aspects: first, before or during the vehicle's travel, the best path from the starting point to the end point is planned according to the destination and road condition data, which is usually a relatively long-term and macroscopic planning process, and the road condition data covers traffic congestion information, etc. Second, during the vehicle's operation, the global path is fine-tuned or re-planned according to the real-time environment perception data, and the algorithm quickly responds and makes decisions to ensure the safety and smooth operation of the vehicle.

[0068] In some embodiments, the target vehicle is simulated to travel according to the vehicle's travel path through a preset simulation algorithm, which consists of a main function, a sensor data collection function, a path planning function, an image processing function, a risk assessment function, and a decision function. The main function is the entry point of the simulation algorithm, which sequentially calls the above functions, simulates the entire workflow of the AEB (Autonomous Emergency Braking) system, and prints the final decision result. The sensor data collection function is used to simulate the process of collecting data from the vehicle's sensors, which in actual application will come from the vehicle's hardware interface. The path planning function is used to receive radar data and image paths from the sensor data collection function and pre-process them. The image processing function simulates the image processing process, which usually involves complex algorithms to detect road types and obstacles in images. The risk assessment function receives radar data and obstacle information and assesses the collision risk. The decision function receives the collision risk level and makes a decision based on the level, where if the risk level is "high", the AEB is activated, otherwise, no action is taken.

[0069] Optionally, the collision risk of the target vehicle is predicted to obtain a collision risk level, and the target vehicle is controlled to brake according to the collision risk level, including: obtaining a deceleration matching table, the deceleration matching table storing a plurality of original parameters, a reference deceleration corresponding to each original parameter, and an advanced deceleration corresponding to each original parameter, wherein the reference deceleration corresponding to the original parameter is less than the advanced deceleration corresponding to the original parameter; in response to identifying the target obstacle corresponding to the target vehicle, obtaining a collision risk parameter, wherein the collision risk parameter includes at least one of the relative distance between the target vehicle and the target obstacle, the relative speed between the target vehicle and the target obstacle, the collision time between the target vehicle and the target obstacle, the tire friction coefficient of the target vehicle, and the tire slip rate of the target vehicle; determining the collision risk level according to the collision risk parameter; if the collision risk level is greater than a preset level threshold and the target vehicle is in a normal area, determining the target deceleration from the reference deceleration according to the matching result between the collision risk parameter and the original parameter, and controlling the target vehicle to brake at the target deceleration, wherein the normal area is different from a wet road area; if the collision risk level is greater than the preset level threshold and the target vehicle is in the wet road area, determining the target deceleration from the advanced deceleration according to the matching result between the collision risk parameter and the original parameter, and controlling the target vehicle to brake at the target deceleration.

[0070] In combination Figure 3 As shown in the figure, the embodiment of the present disclosure provides a vehicle control method for rainy and snowy weather, including:

[0071] Step S301, identifying that the target vehicle is in a wet road area, and jumping to step S302, step S303 and step S304;

[0072] Step S302, displaying an automatic braking function opening identifier in the vehicle;

[0073] Step S303, playing a preset prompt sound in the vehicle;

[0074] Step S304, obtaining a collision risk parameter corresponding to the target vehicle;

[0075] The collision risk parameter includes at least one of the relative distance, the collision time, the tire friction coefficient and the tire slip rate;

[0076] Step S305, determining a target deceleration from a preset deceleration matching table according to the matching result between the collision risk parameter and the original parameter;

[0077] The deceleration matching table stores a plurality of original parameters, an advanced deceleration corresponding to each original parameter;

[0078] Step S306, controlling the target vehicle to brake according to the target deceleration.

[0079] In some embodiments, the time to collision is calculated by the relative speed and the relative distance between the target vehicle and the target obstacle.

[0080] In some embodiments, the time to collision is calculated by formula (3):

[0081]

[0082] In formula (3), TTC is the time to collision, L is the relative distance between the target vehicle and the target obstacle, V is the relative speed between the target vehicle and the target obstacle. rel

[0083] In some embodiments, compared with the automatic braking method for ordinary roads, more redundant distance is needed to prevent the vehicle from colliding due to the slippage and excessive braking distance of the vehicle in the wet and slippery road area, so the deceleration for braking in the wet and slippery road area is greater than the reference deceleration.

[0084] In some embodiments, by adjusting the parameter value of the original parameter, the same deceleration corresponds to different original parameters, which can also achieve the effect of reserving redundant distance.

[0085] In some embodiments, the relationship between the target deceleration and the braking distance is represented by formula (4):

[0086]

[0087] In formula (4), a is the target deceleration, v is the current vehicle speed, and S1 is the braking distance.

[0088] In some embodiments, if the relative distance between the target vehicle and the target obstacle is less than the preset braking distance, the target vehicle is controlled to brake, wherein the preset braking distance is the distance at which the time to collision TTC of the target vehicle is equal to 6s.

[0089] Optionally, the target deceleration is determined from the advanced decelerations according to the matching result between the collision risk parameters and the original parameters, including: determining the intermediate deceleration corresponding to each collision risk parameter from each advanced deceleration according to the matching result between the collision risk parameters and the original parameters, and taking the maximum intermediate deceleration as the target deceleration according to the comparison result between the intermediate decelerations.

[0090] In some embodiments, when the tire friction coefficient is less than 0.15, the advanced deceleration corresponding to the tire friction coefficient is -3.2m / s 2 ​(meters per square second), when the tire friction coefficient is between 0.15-0.2, the tire friction coefficient corresponds to an advanced deceleration of -2.1 m / s 2 , when the tire friction coefficient is greater than 0.2, the tire friction coefficient corresponds to an advanced deceleration of -1 m / s 2 .

[0091] In some embodiments, when the tire slip ratio is less than 10%, the tire slip ratio corresponds to an advanced deceleration of -0.8 m / s 2 ; when the tire slip ratio is between 10%-30%, the tire slip ratio corresponds to an advanced deceleration of -3.5 m / s 2 ; when the tire slip ratio is greater than 30%, the tire slip ratio corresponds to an advanced deceleration of -4.5 m / s 2 .

[0092] Optionally, determining the target deceleration from the advanced decelerations according to the matching results between the collision risk parameters and the original parameters comprises: obtaining parameter priorities corresponding to the collision risk parameters respectively, and taking a collision risk parameter in a first order as a current parameter according to the parameter priorities; in response to the current parameter, obtaining a reference parameter interval corresponding to the current parameter; if the current parameter is within the reference parameter interval, determining the target parameter from the advanced decelerations according to the matching results between the current parameter and the original parameters; if the current parameter is outside the reference parameter interval, taking a collision risk parameter in a next order after the current parameter as a new current parameter according to the parameter priorities.

[0093] In some embodiments, when the target vehicle is located in a wet road area and the speed of the target vehicle is less than 60 km / h (kilometers per hour), when the collision time TTC is greater than 4.5 s (seconds), the collision time TTC corresponds to an advanced deceleration of 0 m / s 2 , when the collision time TTC is between 3 s-4.5 s, the collision time TTC corresponds to an advanced deceleration of -2.5 m / s 2 , when the collision time TTC is less than 3 s, the collision time TTC corresponds to an advanced deceleration of -3.5 m / s 2 ; when the target vehicle is located in a wet road area and the speed of the target vehicle is greater than or equal to 60 km / h, when the collision time TTC is greater than 6 s, the collision time TTC corresponds to an advanced deceleration of 0 m / s 2 , when the collision time TTC is between 4 s-6 s, the collision time TTC corresponds to an advanced deceleration of -3 m / s 2 , when the collision time TTC is less than 4 s, the collision time TTC corresponds to an advanced deceleration of -4 m / s 2 .

[0094] Optionally, if the road surface recognition result meets the preset secondary determination condition, the method further includes: generating road surface prompt information, wherein the road surface prompt information is used to prompt a user in the target vehicle that the target vehicle is in a wet and slippery road surface area.

[0095] In some embodiments, if the target vehicle is in a wet and slippery road surface area, a "snow AEB" or "rain AEB" frame appears on the front windshield and the center control display screen, and at the same time, the system plays a preset prompt sound, such as "dunk dunk" sound, thereby prompting the user that the target vehicle is in a wet and slippery road surface area.

[0096] Optionally, if the road surface recognition result meets the preset secondary determination condition, the method further includes: if the relative distance between the target vehicle and the target obstacle is less than a preset warning distance, generating risk prompt information, wherein the risk prompt information is used to prompt a user in the target vehicle that the target vehicle has a collision risk.

[0097] Optionally, the target vehicle is provided with an environmental algorithm model, and the environmental algorithm model includes a target recognition model and / or an environmental perception model, wherein the target recognition model is used for target recognition of a road surface on which the target vehicle travels, and the environmental perception model is used for identifying a target obstacle corresponding to the target vehicle

[0098] Optionally, the method further includes: iteratively training the environmental algorithm model according to preset training sample data to optimize model parameters of the environmental algorithm model.

[0099] In some embodiments, iteratively training the environmental algorithm model in the target vehicle through the training sample data includes: collecting a large, diverse and high-quality data set, which includes samples from various real scenarios to fully reflect the complexity of the real world; accurately labeling the collected data to ensure that the model can learn the correct features and categories; using these data to train and optimize the recognition model, and through the iterative training process, continuously adjusting the parameters and structure of the model to improve its recognition accuracy and generalization ability.

[0100] In some embodiments, advanced technologies such as deep learning are used to enable the environmental algorithm model to automatically extract useful features from raw data without manually designing features, and by fusing multiple sources and types of features, the complementarity of various information is fully utilized to improve recognition accuracy.

[0101] In some embodiments, the environmental algorithm model receives new data samples and updates its internal parameters and structure in real time to adapt to new environments and scenarios; and by using models that have been trained in related fields or scenarios, the model quickly adapts to new recognition tasks through fine-tuning and other methods, reducing the need for new data and training time.

[0102] Optionally, the method further comprises: performing parameter optimization on the environmental algorithm model according to user feedback data corresponding to the environmental algorithm model.

[0103] In some embodiments, user feedback information is collected to understand the performance of the model in actual application and to make targeted improvements according to the feedback.

[0104] Optionally, the method further comprises: iteratively updating the environmental algorithm model according to the model accuracy corresponding to the environmental algorithm model until the model accuracy reaches a preset accuracy.

[0105] In some embodiments, the identification performance of the model is periodically evaluated to ensure accuracy, so as to monitor the stability and effectiveness of the model.

[0106] Optionally, the method further comprises: obtaining environmental sample data corresponding to different environmental requirements, and iteratively training the environmental algorithm model according to each environmental sample data to optimize the model parameters of the environmental algorithm model, wherein the environmental requirements include one or more of illumination conditions, environmental conditions, and temperature conditions.

[0107] In some embodiments, the identification requirements and challenges in different scenarios are analyzed in depth, and the specific scenarios are optimized and adjusted; and the adaptability of the target identification model to different illumination conditions, weather conditions, obstacles and other environmental factors is improved, so as to ensure high identification accuracy in various complex environments.

[0108] In combination with Figure 4 As shown in the figure, the embodiments of the present disclosure provide a vehicle control method for rainy and snowy weather, which comprises:

[0109] Step S401, obtaining weather-related parameters corresponding to a target vehicle;

[0110] The weather-related parameters include driving environment parameters and / or tire adhesion parameters.

[0111] Step S402, determining whether the weather-related parameters meet a first-level determination condition, if yes, jumping to step S403, if not, jumping to step S401;

[0112] The first-level determination condition is determined by vehicle testing in different test environments, and the test environments include rainy and snowy weather environments.

[0113] Step S403, generating road condition information according to vehicle-road cooperation data and network map data, and broadcasting the road condition information to a user in the target vehicle;

[0114] Step S404, performing target identification on the road surface of the road on which the target vehicle travels to obtain a road surface identification result, and performing path planning according to each sensor parameter to obtain a vehicle travel path of the target vehicle.

[0115] In step S406, if the road surface recognition result includes a wet and slippery road surface region, the target vehicle and the wet and slippery road surface region are mapped to a vehicle driving path, and the driving of the target vehicle is simulated according to the vehicle driving path.

[0116] In step S407, it is determined whether the target vehicle meets a secondary determination condition. If yes, the process jumps to step S408. If no, the process jumps to step S404.

[0117] The secondary determination condition includes that the target vehicle is in the wet and slippery road surface region.

[0118] In step S408, the collision risk of the target vehicle is predicted to obtain a collision risk level.

[0119] In step S409, the target vehicle is controlled to brake according to the collision risk level.

[0120] By using the vehicle control method for rainy and snowy weather provided in the embodiments of the present disclosure, the weather-related parameters corresponding to the target vehicle are obtained, and if the weather-related parameters meet a preset primary determination condition, the road surface on which the target vehicle drives is identified as a snowy road to obtain a wet and slippery road surface region in the road surface. Thus, when the target vehicle drives in the wet and slippery road surface region, the automatic braking function of the target vehicle is started. In this way, if the weather-related parameters meet the rainy and snowy weather condition, it is determined that snow may appear on the road surface, so the road surface on which the target vehicle drives is identified as a snowy road to obtain a wet and slippery road surface region, and when the vehicle is in the wet and slippery road surface region, the target vehicle is controlled to brake according to the collision risk level, so that the automatic emergency braking of the vehicle in the wet and slippery road surface region is realized, the vehicle in the wet and slippery road surface region is provided with obstacle avoidance support, and the safety of the vehicle driving is improved.

[0121] In combination with FIG. 1, Figure 5 The embodiments of the present disclosure provide a system architecture for implementing the vehicle control method for rainy and snowy weather, which includes:

[0122] The sensor layer includes an image sensor, a radar sensor, a tire rotation speed sensor, a temperature sensor, a vehicle-road cooperative system, and a map system. The image sensor is configured to collect images around the target vehicle to obtain environment images. The radar sensor is configured to collect point cloud data around the target vehicle. The tire rotation speed sensor is configured to collect the vehicle speed of the target vehicle. The temperature sensor is configured to collect the environment temperature of the environment in which the target vehicle is located. The vehicle-road cooperative system is configured to collect environment information around the vehicle. The map system is configured to collect map data from a server end.

[0123] The first control layer is configured to generate road condition information of the target vehicle according to the vehicle-road cooperative data and the network map data if the weather-related parameter meets the preset first determination condition; perform target recognition on a road surface on which the target vehicle travels to obtain a road surface recognition result; map the target vehicle and a wet and slippery road surface region to a vehicle travel path, and simulate travel of the target vehicle according to the vehicle travel path.

[0124] The risk assessment layer is configured to predict a collision risk of the target vehicle to obtain a collision risk level if the road surface recognition result meets the preset second determination condition.

[0125] The decision layer is configured to control the target vehicle to brake according to the collision risk level.

[0126] In combination Figure 6 As shown in FIG. 1, the embodiment of the present disclosure provides a vehicle control system for rainy and snowy weather, which includes an acquisition module 601, a first determination module 602, and a second determination module 603.

[0127] The acquisition module 601 is configured to acquire a weather-related parameter corresponding to a target vehicle, wherein the weather-related parameter includes a travel environment parameter and / or a tire adhesion parameter.

[0128] The first determination module 602 is configured to perform target recognition on a road surface on which the target vehicle travels to obtain a road surface recognition result if the weather-related parameter meets a preset first determination condition, wherein the first determination condition is determined by vehicle testing in different test environments, and the test environments include a rainy and snowy weather environment.

[0129] The second determination module 603 is configured to predict a collision risk of the target vehicle to obtain a collision risk level if the road surface recognition result meets a preset second determination condition, so as to control the target vehicle to brake according to the collision risk level, wherein the second determination condition includes that the target vehicle is in a wet and slippery road surface region.

[0130] The vehicle control system for rainy and snowy weather provided by the embodiment of the present disclosure acquires a weather-related parameter corresponding to a target vehicle, and performs snow identification on a road surface on which the target vehicle travels to obtain a wet and slippery road surface region in the road surface if the weather-related parameter meets a preset first determination condition, so as to control the target vehicle to start an automatic braking function when the target vehicle travels in the wet and slippery road surface region. In this way, if the weather-related parameter meets the rainy and snowy weather condition, it is determined that snow may appear on the road surface, so that snow identification is performed on the road surface on which the target vehicle travels to obtain the wet and slippery road surface region, and the target vehicle is controlled to brake according to the collision risk level when the vehicle is in the wet and slippery road surface region, thereby realizing automatic emergency braking of the vehicle in the wet and slippery road surface region, providing obstacle avoidance support for the vehicle in the wet and slippery road surface region, and improving the safety of vehicle travel.

[0131] The embodiments of the present disclosure further provide a vehicle terminal, comprising: a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory, so that the vehicle terminal executes the method described above.

[0132] Figure 7 A structural schematic diagram of a computer system of a vehicle terminal suitable for implementing the embodiments of the present application is shown. It should be noted that, Figure 7 The computer system 700 of the vehicle terminal shown is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0133] As Figure 7 shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 702 or programs loaded from a storage portion 708 into a random access memory (RAM) 703, such as performing the methods in the above embodiments. In the RAM 703, various programs and data required for system operation are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0134] The following components are connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker, and the like; a storage portion 708 including a hard disk, and the like; and a communication portion 709 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 710 as needed, so that a computer program read therefrom is installed in the storage portion 708 as needed.

[0135] The vehicle terminal disclosed in the embodiment comprises a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected with the processor and the transceiver and complete communication with each other. The memory is used for storing a computer program. The communication interface is used for communication. The processor and the transceiver are used for running the computer program, so that the vehicle terminal executes each step of the method.

[0136] The above description and drawings sufficiently illustrate the embodiments of the present disclosure to enable one skilled in the art to practice them. Other embodiments can include structural, logical, electrical, process, and other changes. The embodiments are merely representative of the possible variations. Individual components and functions are optional unless explicitly required, and the order of operations can be changed. Parts and sub-embodiments of some embodiments can be included or replaced by parts and sub-embodiments of other embodiments. Furthermore, the words used in this application are only used to describe the embodiments and not to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms as well. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations of one or more associated listed items. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" and the like mean the presence of the stated sub-embodiments, whole, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other sub-embodiments, whole, steps, operations, elements, components and / or groups of these. Without more limitations, the element defined by the statement "comprises one" does not exclude the presence of another identical element in the process, method or device comprising the element. In this document, each embodiment focuses on the differences from other embodiments, and the same or similar parts between various embodiments can be referred to each other. For the method, product, etc. disclosed in the embodiments, if it corresponds to the method part disclosed in the embodiments, the relevant part can be referred to the description of the method part.

[0137] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of the present disclosure. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0138] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of units can be merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some sub-samples can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms. The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to implement the embodiments. In addition, each functional unit in the embodiments of the present disclosure can be integrated in one processing unit, or each unit can be a physically independent unit, or two or more units can be integrated in one unit.

[0139] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

Claims

1. A vehicle control method for snowy weather, characterized by, The method comprises: acquiring weather-related parameters corresponding to the target vehicle, wherein the weather-related parameters comprise driving environment parameters and / or tire adhesion parameters; if the weather-related parameters meet a preset first-level determination condition, performing target recognition on the road surface on which the target vehicle travels to obtain a road surface recognition result, wherein the first-level determination condition is determined by vehicle testing in different test environments, and the test environments comprise rainy and snowy weather environments; if the road surface recognition result meets a preset second-level determination condition, predicting a collision risk of the target vehicle to obtain a collision risk level, and controlling the target vehicle to brake according to the collision risk level, wherein the second-level determination condition comprises that the target vehicle is in a wet and slippery road surface area; The method further comprises collecting data by a plurality of vehicle sensors arranged on the target vehicle to obtain sensor parameters collected by each of the vehicle sensors; and performing path planning according to each of the sensor parameters to obtain a vehicle travel path of the target vehicle. According to each of the sensor parameters, performing path planning to obtain a vehicle travel path of the target vehicle, comprising: classifying each of the sensor parameters according to different parameter types, and performing data fusion on sensor parameters of the same parameter type to obtain fusion data, wherein the fusion data comprises global data and real-time data, the global data comprises map data and / or road condition data, and the real-time data comprises image sensor data and / or radar sensor data; if the global data comprises map data, setting a starting position and a target position in the map data to perform path planning between the starting position and the target position according to the global data to obtain a vehicle travel path; performing environmental perception on the environment in which the target vehicle is located according to the real-time data to obtain environmental perception data, and adjusting the vehicle travel path according to the environmental perception data to avoid collision of the target vehicle with a target obstacle, wherein the environmental perception data comprises an obstacle position and / or an obstacle motion trajectory corresponding to the target obstacle.

2. The method of claim 1, wherein, If the weather-related parameters meet the preset first-level determination condition, the method further comprises: acquiring car-road cooperation data and network map data; generating road condition information of the target vehicle according to the car-road cooperation data and the network map data; playing the road condition information to a user in the target vehicle.

3. The method of claim 1, wherein, Determine whether the road surface recognition result meets the second-level determination condition in the following way: if the road surface recognition result comprises a wet and slippery road surface area, map the target vehicle and the wet and slippery road surface area to the vehicle travel path, and simulate target vehicle travel according to the vehicle travel path to determine whether the target vehicle travels in the wet and slippery road surface area according to the simulation result.

4. The method according to any one of claims 1 to 3, characterized in that, Predicting a collision risk of the target vehicle to obtain a collision risk level, and controlling the target vehicle to brake according to the collision risk level, comprises: obtain a deceleration matching table, the deceleration matching table storing a plurality of original parameters, a reference deceleration corresponding to each of the original parameters, and an advanced deceleration corresponding to each of the original parameters, wherein the reference deceleration corresponding to the original parameter is less than the advanced deceleration corresponding to the original parameter; obtain a collision risk parameter in response to identifying the target obstacle corresponding to the target vehicle, wherein the collision risk parameter comprises at least one of a relative distance between the target vehicle and the target obstacle, a relative speed between the target vehicle and the target obstacle, a collision time between the target vehicle and the target obstacle, a tire friction coefficient of the target vehicle, and a tire slip rate of the target vehicle; determine a collision risk level according to the collision risk parameter; if the collision risk level is greater than a preset level threshold and the target vehicle is in a normal area, determine a target deceleration from the reference deceleration according to a matching result between the collision risk parameter and the original parameter, and control the target vehicle to brake at the target deceleration, wherein the normal area is different from the wet and slippery road area; if the collision risk level is greater than the preset level threshold and the target vehicle is in the wet and slippery road area, determine a target deceleration from the advanced deceleration according to a matching result between the collision risk parameter and the original parameter, and control the target vehicle to brake at the target deceleration.

5. The method of claim 4, wherein, determining a target deceleration from the advanced deceleration according to a matching result between the collision risk parameter and the original parameter comprises at least one of: determining an intermediate deceleration corresponding to each of the collision risk parameters from each of the advanced decelerations according to a matching result between the collision risk parameter and the original parameter, and determining the target deceleration as the maximum intermediate deceleration according to a comparison result between each of the intermediate decelerations; obtaining a parameter priority corresponding to each of the collision risk parameters, and determining a collision risk parameter in a first order as a current parameter according to the parameter priority; obtaining a reference parameter interval corresponding to the current parameter in response to the current parameter; if the current parameter is within the reference parameter interval, determining a target parameter from each of the advanced decelerations according to a matching result between the current parameter and the original parameter, and if the current parameter is outside the reference parameter interval, determining a collision risk parameter in a next order after the current parameter as a new current parameter according to the parameter priority.

6. The method of claim 4, wherein, if the road surface identification result meets a preset secondary determination condition, the method further comprises at least one of: generating road surface prompt information, wherein the road surface prompt information is used to prompt a user in the target vehicle that the target vehicle is in the wet and slippery road area; if the relative distance between the target vehicle and the target obstacle is less than a preset warning distance, generating risk prompt information, wherein the risk prompt information is used to prompt a user in the target vehicle that the target vehicle has a collision risk.

7. The method of claim 4, wherein, the method further comprises: According to the preset training sample data, the environment algorithm model is iteratively trained to optimize the model parameters of the environment algorithm model, wherein the environment algorithm model comprises a target recognition model and / or an environment perception model, the target recognition model is used for target recognition of a road surface on which the target vehicle travels, and the environment perception model is used for identifying a target obstacle corresponding to the target vehicle; According to the user feedback data corresponding to the environment algorithm model, the parameters of the environment algorithm model are optimized; According to the model accuracy corresponding to the environment algorithm model, the environment algorithm model is iteratively updated until the model accuracy reaches a preset accuracy; Different environment sample data corresponding to different environment requirements are obtained, and the environment algorithm model is iteratively trained according to each environment sample data to optimize the model parameters of the environment algorithm model, wherein the environment requirements include one or more of light conditions, environment conditions, and temperature conditions.

8. A vehicle control system against snow weather, characterized by, Comprise: The acquisition module is used for acquiring weather-related parameters corresponding to the target vehicle, wherein the weather-related parameters include driving environment parameters and / or tire adhesion parameters; The first-level determination module is used for identifying the target vehicle if the weather-related parameters meet the preset first-level determination condition, identifying the road surface on which the target vehicle travels, and obtaining a road surface recognition result, wherein the first-level determination condition is determined by vehicle testing in different test environments, and the test environment includes a rainy and snowy weather environment; The second-level determination module is used for predicting the collision risk of the target vehicle if the road surface recognition result meets the preset second-level determination condition, obtaining a collision risk level, and controlling the target vehicle to brake according to the collision risk level, wherein the second-level determination condition includes that the target vehicle is in a wet and slippery road surface area; The second-level determination module is also used for collecting data through a plurality of vehicle sensors arranged on the target vehicle to obtain sensor parameters collected by each vehicle sensor; and performing path planning according to each sensor parameter to obtain a vehicle driving path of the target vehicle; The secondary determination module obtains the vehicle driving path of the target vehicle by classifying each sensor parameter according to different parameter types and fusing sensor parameters of the same parameter type to obtain fusion data, wherein the fusion data includes global data and real-time data, the global data includes map data and / or road condition data, the real-time data includes image sensor data and / or radar sensor data; if the global data includes map data, a starting position and a target position are set in the map data to plan a path between the starting position and the target position according to the global data to obtain a vehicle driving path; environment perception is performed on the environment in which the target vehicle is located according to the real-time data to obtain environment perception data, and the vehicle driving path is adjusted according to the environment perception data to avoid the target vehicle colliding with a target obstacle, wherein the environment perception data includes an obstacle position and / or an obstacle motion trajectory corresponding to the target obstacle.

9. A vehicle terminal, characterized by Comprise: A processor and a memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the vehicle terminal executes the method according to any one of claims 1 to 7.

Images